Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.7705. Min Act: -0.1700
Data Index: 3930700 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.6768. Min Act: -0.1700
Data Index: 1142485 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.6455. Min Act: -0.1700
Data Index: 5403556 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.5830. Min Act: -0.1700
Data Index: 476096 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.5830. Min Act: -0.1700
Data Index: 4945044 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.5518. Min Act: -0.1700
Data Index: 1724368 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.5518. Min Act: -0.1700
Data Index: 1875553 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.5205. Min Act: -0.1700
Data Index: 4961626 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4893. Min Act: -0.1700
Data Index: 8373416 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4893. Min Act: -0.1700
Data Index: 2089919 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4893. Min Act: -0.1700
Data Index: 4828162 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4268. Min Act: -0.1700
Data Index: 3833580 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4268. Min Act: -0.1700
Data Index: 3516365 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4580. Min Act: -0.1700
Data Index: 8012250 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4580. Min Act: -0.1700
Data Index: 4044227 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4268. Min Act: -0.1700
Data Index: 4643908 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.3955. Min Act: -0.1700
Data Index: 4852447 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4268. Min Act: -0.1700
Data Index: 8373415 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.4268. Min Act: -0.1700
Data Index: 4275872 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7705. Min Range: -6.7705
Max Act: 6.3955. Min Act: -0.1700
Data Index: 358851 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19